NLP Applications

Fabrizio Sebastiani
Director of Research
Alejandro Moreo
Senior Researcher

This research area focuses on the development of NLP and AI algorithms and methodologies, with particular emphasis on their application to various aspects of text analysis. Over the years, we have conducted extensive research on representation learning for text classification, including both cross-lingual and cross-domain scenarios, as well as robust representation learning for handling misspellings. Our work also covers sentiment classification, sequence learning for information extraction, cost-sensitive text classification, and the application of these methods to domains such as authorship analysis, technology-assisted review, and native language identification.

Research Topics

Selected Publications

2025
Misspellings in Natural Language Processing: A survey.
Gianluca Sperduti and Alejandro Moreo.
ArXiv preprint.
2024
A Simple Method for Classifier Accuracy Prediction Under Prior Probability Shift.
Lorenzo Volpi, Alejandro Moreo, and Fabrizio Sebastiani.
Discovery Science - 27th International Conference, DS 2024, Pisa, Italy, October 14-16, 2024, Proceedings, Part II.
2024
Explainable Authorship Identification in Cultural Heritage Applications.
Mattia Setzu, Silvia Corbara, Anna Monreale, Alejandro Moreo, and Fabrizio Sebastiani.
ACM Journal on Computing and Cultural Heritage 17(3).
2023
Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification.
Alejandro Moreo, Andrea Pedrotti, and Fabrizio Sebastiani.
ACM Transactions on Information Systems 41(2).